公开(公告)号：US12033670B2

公开(公告)日：2024-07-09

申请号：US17810651

申请日：2022-07-05

Applicant: ADOBE INC.

Inventor： Seoungwug Oh ,  Joon-Young Lee ,  Jingwan Lu ,  Kwanggyoon Seo

IPC: G11B27/036 ,  G06T7/30 ,  G06T11/60 ,  G06V10/776 ,  G06V20/40 ,  G06V40/16

CPC classification number: G11B27/036 ,  G06T7/30 ,  G06T11/60 ,  G06V10/776 ,  G06V20/46 ,  G06V40/171 ,  G06V40/176 ,  G06T2207/10016 ,  G06T2207/20212 ,  G06T2207/30201 ,  G06T2210/22

Abstract: Systems and methods for video processing are described. Embodiments of the present disclosure identify an image that depicts an expression of a face; encode the image to obtain a latent code representing the image; edit the latent code to obtain an edited latent code that represents the face with a target attribute that is different from an original attribute of the face and with an edited expression that is different from the expression of the face; modify the edited latent code to obtain a modified latent code that represents the face with the target attribute and a modified expression, wherein a difference between the expression and the modified expression is less than a difference between the expression and the edited expression; and generate a modified image based on the modified latent code, wherein the modified image depicts the face with the target attribute and the modified expression.

公开(公告)号：US20240013809A1

公开(公告)日：2024-01-11

申请号：US17810651

申请日：2022-07-05

Applicant: ADOBE INC.

Inventor： Seoungwug Oh ,  Joon-Young Lee ,  Jingwan Lu ,  Kwanggyoon Seo

IPC: G11B27/036 ,  G06V20/40 ,  G06V40/16 ,  G06T11/60 ,  G06T7/30 ,  G06V10/776

CPC classification number: G11B27/036 ,  G06V20/46 ,  G06V40/176 ,  G06V40/171 ,  G06T11/60 ,  G06T7/30 ,  G06V10/776 ,  G06T2210/22 ,  G06T2207/20212 ,  G06T2207/30201 ,  G06T2207/10016

Abstract: Systems and methods for video processing are described. Embodiments of the present disclosure identify an image that depicts an expression of a face; encode the image to obtain a latent code representing the image; edit the latent code to obtain an edited latent code that represents the face with a target attribute that is different from an original attribute of the face and with an edited expression that is different from the expression of the face; modify the edited latent code to obtain a modified latent code that represents the face with the target attribute and a modified expression, wherein a difference between the expression and the modified expression is less than a difference between the expression and the edited expression; and generate a modified image based on the modified latent code, wherein the modified image depicts the face with the target attribute and the modified expression.

公开(公告)号：US11803971B2

公开(公告)日：2023-10-31

申请号：US17319979

申请日：2021-05-13

Applicant: Adobe Inc.

Inventor： Jaedong Hwang ,  Seoung Wug Oh ,  Joon-Young Lee

IPC: G06T7/11 ,  G06V10/40 ,  G06F18/2413

CPC classification number: G06T7/11 ,  G06F18/24137 ,  G06V10/40 ,  G06T2207/20084

Abstract: This disclosure describes one or more implementations of a panoptic segmentation system that generates panoptic segmented digital images that classify both known and unknown instances of digital images. For example, the panoptic segmentation system builds and utilizes a panoptic segmentation neural network to discover, cluster, and segment new unknown object subclasses for previously unknown object instances. In addition, the panoptic segmentation system can determine additional unknown object instances from additional digital images. Moreover, in some implementations, the panoptic segmentation system utilizes the newly generated unknown object subclasses to refine and tune the panoptic segmentation neural network to improve the detection of unknown object instances in input digital images.

公开(公告)号：US11682126B2

公开(公告)日：2023-06-20

申请号：US17080812

申请日：2020-10-26

Applicant: ADOBE INC.

Inventor： Kalyan Krishna Sunkavalli ,  Sunil Hadap ,  Joon-Young Lee ,  Zhuo Hui

IPC: G06T7/49 ,  G01N21/55 ,  G06T7/90 ,  G06T7/40 ,  G06T3/00 ,  G06T7/60 ,  G06T17/00

CPC classification number: G06T7/49 ,  G01N21/55 ,  G06T3/0068 ,  G06T7/40 ,  G06T7/60 ,  G06T7/90 ,  G06T17/00 ,  G06T2200/08 ,  G06T2207/10016 ,  G06T2207/10152

Abstract: Methods and systems are provided for performing material capture to determine properties of an imaged surface. A plurality of images can be received depicting a material surface. The plurality of images can be calibrated to align corresponding pixels of the images and determine reflectance information for at least a portion of the aligned pixels. After calibration, a set of reference materials from a material library can be selected using the calibrated images. The set of reference materials can be used to determine a material model that accurately represents properties of the material surface.

公开(公告)号：US20220375090A1

公开(公告)日：2022-11-24

申请号：US17319979

申请日：2021-05-13

Applicant: Adobe Inc.

Inventor： Jaedong Hwang ,  Seoung Wug Oh ,  Joon-Young Lee

IPC: G06T7/11 ,  G06K9/62 ,  G06K9/46

Abstract: This disclosure describes one or more implementations of a panoptic segmentation system that generates panoptic segmented digital images that classify both known and unknown instances of digital images. For example, the panoptic segmentation system builds and utilizes a panoptic segmentation neural network to discover, cluster, and segment new unknown object subclasses for previously unknown object instances. In addition, the panoptic segmentation system can determine additional unknown object instances from additional digital images. Moreover, in some implementations, the panoptic segmentation system utilizes the newly generated unknown object subclasses to refine and tune the panoptic segmentation neural network to improve the detection of unknown object instances in input digital images.

公开(公告)号：US20210409836A1

公开(公告)日：2021-12-30

申请号：US17470441

申请日：2021-09-09

Applicant: Adobe Inc.

Inventor： Bryan Russell ,  Ruppesh Nalwaya ,  Markus Woodson ,  Joon-Young Lee ,  Hailin Jin

IPC: H04N21/81 ,  H04N21/845 ,  G06N3/08 ,  G06K9/00

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for automatic tagging of videos. In particular, in one or more embodiments, the disclosed systems generate a set of tagged feature vectors (e.g., tagged feature vectors based on action-rich digital videos) to utilize to generate tags for an input digital video. For instance, the disclosed systems can extract a set of frames for the input digital video and generate feature vectors from the set of frames. In some embodiments, the disclosed systems generate aggregated feature vectors from the feature vectors. Furthermore, the disclosed systems can utilize the feature vectors (or aggregated feature vectors) to identify similar tagged feature vectors from the set of tagged feature vectors. Additionally, the disclosed systems can generate a set of tags for the input digital videos by aggregating one or more tags corresponding to identified similar tagged feature vectors.

公开(公告)号：US10600150B2

公开(公告)日：2020-03-24

申请号：US15339017

申请日：2016-10-31

Applicant: Adobe Inc.

Inventor： Byungmoon Kim ,  Joon-Young Lee ,  Jinwoong Jung ,  Gavin Miller

IPC: G06T3/00 ,  H04N5/232 ,  G06F3/0346 ,  G06F3/01 ,  H04N5/262

Abstract: The present disclosure includes methods and systems for modifying orientation of a spherical panorama digital image based on an inertial measurement device. In particular, one or more embodiments of the disclosed systems and methods correct for tilt and/or roll in a digital camera utilized to capture a spherical panorama digital images by detecting changes in orientation to an inertial measurement device and generating an enhanced spherical panorama digital image based on the detect changes. In particular, in one or more embodiments, the disclosed systems and methods modify orientation of a spherical panorama digital image in three-dimensional space based on changes in orientation to an inertial measurement device and resample pixels based on the modified orientation to generate an enhanced spherical panorama digital image.

公开(公告)号：US20190325275A1

公开(公告)日：2019-10-24

申请号：US15957419

申请日：2018-04-19

Applicant: Adobe Inc.

Inventor： Joon-Young Lee ,  Hailin Jin ,  Fabian David Caba Heilbron

IPC: G06K9/66 ,  G06N3/08 ,  G06N3/04 ,  G06K9/00 ,  G06K9/62

Abstract: Various embodiments describe active learning methods for training temporal action localization models used to localize actions in untrimmed videos. A trainable active learning selection function is used to select unlabeled samples that can improve the temporal action localization model the most. The select unlabeled samples are then annotated and used to retrain the temporal action localization model. In some embodiment, the trainable active learning selection function includes a trainable performance prediction model that maps a video sample and a temporal action localization model to a predicted performance improvement for the temporal action localization model.

公开(公告)号：US20190311202A1

公开(公告)日：2019-10-10

申请号：US15949935

申请日：2018-04-10

Applicant: Adobe Inc.

Inventor： Joon-Young Lee ,  Seoungwug Oh ,  Kalyan Krishna Sunkavalli

IPC: G06K9/00 ,  G06T7/155 ,  G06K9/62 ,  G06T9/00

Abstract: Various embodiments describe video object segmentation using a neural network and the training of the neural network. The neural network both detects a target object in the current frame based on a reference frame and a reference mask that define the target object and propagates the segmentation mask of the target object for a previous frame to the current frame to generate a segmentation mask for the current frame. In some embodiments, the neural network is pre-trained using synthetically generated static training images and is then fine-tuned using training videos.